| Title: | Predicting Susceptibility to Cirrhosis and Liver Transplantation using Machine Learning Algorithms |
| Lead Institution: | University Health Network |
| Principal investigator: | Dr Mamatha Bhat |
Application 53976
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
About
Patients with liver disease often present to physicians once they develop fatal complications such as digestive tract bleeding, ascites and hepatocellular carcinoma. In fact, liver-related mortality represents the 8th leading reason for years of life lost in the U.S. The onset of these complications is predated by years of disease with no symptoms, resulting in delayed diagnosis. Intervention during this period has the potential to prevent worsening liver failure, and even result in improvement in liver scarring. This is particularly important given that the liver is an organ whose function cannot be replaced by dialysis. Primary objective: To develop a calculator using artificial intelligence tools on clinical, laboratory and genetic data over time to predict those individuals who will develop chronic liver disease, associated cirrhosis and need for liver transplant Secondary objectives: To predict which patients with liver disease are at risk of all-cause death, heart attacks and death, liver cancer and other cancers, as well as cancer-related death. Liver disease is currently often diagnosed when it is too late to intervene. The ability to implement a MLA to detect patients at risk of cirrhosis, its complications and comorbidities will enable implementation of preventive practices before the onset of these fatal complications.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 10876 | Machine Learning Approach to Classify Cardiovascular Disease in Patients With Nonalcoholic Fatty Liver Disease in the UK Biobank Cohort | Divya Sharma (+5) | 2021 | Journal of the American Heart Association |
Enabling scientific discoveries that improve human health